OPUS-CAT: Desktop NMT with CAT integration and local fine-tuning

Tommi Nieminen

Demo Paper

Gather-1F: Apr 21, Gather-1F: Apr 21 (13:00-15:00 UTC) [Join Gather Meeting]

You can open the pre-recorded video in separate windows.

Abstract: OPUS-CAT is a collection of software which enables translators to use neural machine translation in computer-assisted translation tools without exposing themselves to security and confidentiality risks inherent in online machine translation. OPUS-CAT uses the public OPUS-MT machine translation models, which are available for over a thousand language pairs. The generic OPUS-MT models can be fine-tuned with OPUS-CAT on the desktop using data for a specific client or domain.
NOTE: Video may display a random order of authors. Correct author list is at the top of this page.

Similar Papers

Revisiting Multi-Domain Machine Translation
Minh Quang Pham, Josep Maria Crego, François Yvon,
Finite-state script normalization and processing utilities: The Nisaba Brahmic library
Cibu Johny, Lawrence Wolf-Sonkin, Alexander Gutkin, Brian Roark,
Breaking Writer's Block: Low-cost Fine-tuning of Natural Language Generation Models
Alexandre Duval, Thomas Lamson, Gaël de Léséleuc de Kérouara, Matthias Gallé,
Context-aware Neural Machine Translation with Mini-batch Embedding
Makoto Morishita, Jun Suzuki, Tomoharu Iwata, Masaaki Nagata,